3 papers
cs.IT2024
Federated Learning via Lattice Joint Source-Channel Coding
Seyed Mohammad Azimi-Abarghouyi, Lav R. Varshney
This paper introduces a universal federated learning framework that enables over-the-air computation via digital communications, using a new joint source-channel coding scheme. Wit…
cs.IT2024
Hierarchical Over-the-Air Federated Learning with Awareness of Interference and Data Heterogeneity
Seyed Mohammad Azimi-Abarghouyi, Viktoria Fodor
When implementing hierarchical federated learning over wireless networks, scalability assurance and the ability to handle both interference and device data heterogeneity are crucia…
cs.IT2014
Distributed Compute-and-Forward Based Relaying Strategies in Multi-User Multi-Relay Networks
Seyed Mohammad Azimi-Abarghouyi, Mohsen Hejazi, Masoumeh Nasiri-Kenari
In this paper, we propose different practical distributed schemes to solve the rank failure problem in the compute and forward (CMF)-based multi-user multi-relay networks without c…